Workshop Registration is Open!!! Register here
(Author Registration by May 1st, General Registration by May 12th)
Medical Cyber-Physical Systems (CPS) encompass a new generation of smart medical systems that integrate human, cyber, and physical elements in closed-loop control. They aim to improve patient care by enabling the delivery of advanced therapies and complex surgeries. An example is the artificial pancreas that allows people with diabetes to better manage their condition. Another example is medical robotic systems, which allow doctors to perform minimally-invasive surgeries that were not possible before. Such systems may be integrated into the Internet of Medical Things (IoMT) which consist of connected infrastructures of medical devices, mobile and web applications, and other health services. Designing safe and effective Medical CPS and IoMT involves the work of a multi-disciplinary team of engineers, medical domain experts, and human factors specialists. This work needs to be supported by rigorous development processes and tools, as substantial evidence needs to be documented and integrated to justify design choices and ease the review process mandated by regulation.
The objectives of the Medical Cyber-Physical Systems (MCPS) and Internet of Medical Things workshop 2021 are to provide opportunities for researchers, industrial practitioners, caregivers, and government agencies to demonstrate innovative development methods and tools, present experience reports, discuss open challenges, and explore ideas for future development of Medical CPS and the Internet of Medical Things. Contributions are welcome on all aspects of system development, including specification, design, analysis, implementation, documentation, and certification of Medical CPS. Demonstrations of existing tools for design and analysis of Medical CPS are also encouraged.
The 11th MCPS workshop will be an one-day virtual event co-located with CPS-IOT Week 2021. Topics of interest include, but are not limited to, the following:
|March 12th, 2021||Submission Deadline (Papers/Posters/Demos)|
|March 22nd, 2021||Notification of Acceptance||March 29th, 2021||Camera Submission Due|
|May 18th, 2021||Workshop|
Call for papers [pdf]
Submissions are due March 12th, 2021. We are accepting the following types of submissions:
Submit your papers via EasyChair - https://easychair.org/conferences/?conf=mcps2021
Authors should prepare their papers using LaTeX and the ACM style file (SIGCONF). Submissions must be original and should not have been published previously or be under consideration for publication while being evaluated for this workshop. Reviews will be single blind.
Accepted papers will be included in the CPS week proceedings. By submitting to the workshop the authors are granting permission for ACM to publish in print and digital formats for the ACM archive. Note that the copyright remains with authors.
Workshop Zoom Link
Meeting ID: 932 0518 1087, Passcode: 341957
Slack Channel Link
Workshop Agenda: Times are in U.S. / Canada Eastern Time
Keynote Talk: Machine Learning for Decision Support and Personalised Care
Tingting Zhu, University of Oxford
Raproto: an open source platform for rapid prototyping of wearable medical devices
Amanda Watson, Hyonyoung Choi, Insup Lee, James Weimer
Inference-based subject atypicality and signal quality indicators for physiological data
Ali Tivay, George C. Kramer, Jin-Oh Hahn
Understanding autism: the power of EEG harnessed by prototypical learning
Asif Salekin, Natalie Russo
Robust monitoring for medical cyber-physical systems
Bernd Finkbeiner, Andreas Keller, Jessica Schmidt, Maximilian Schwenger
For researchers, especially in remote health monitoring and ubiquitous computing, it is common to expend a significant amount of time and effort to develop data collection systems that can be used outside of the lab or clinic. These systems tend to be customized and highly specific to the task at hand; thus, they are not general enough to support other tasks. In this paper, we present Raproto, an open-source, easy-to-use rapid prototyping platform that facilitates data collection and visualization from sensors on commercially available, off-the-shelf smartwatches. The Raproto platform consists of three components: the smartwatch, communication protocol, and server. These components support the collection, transmission, storage, analysis, and visualization of data. We evaluate our platform on limiting factors including the smartwatch battery life, data loss during transmission, and data latency. Overall, we find that the smartwatch can last for over 24 hours on a single charge, has little to no data loss, and less than a second of data latency per transmission.
Physiological measurements are an integral part of many established and emerging engineering and biomedical applications that involve physiological modeling, physiological state estimation, and physiological closed loop control. In practice, such measurements exhibit a large degree of variability, which is apparent at multiple levels, including disturbances acting on measured signals and unexpected physiological behavior in certain individuals. In this short paper, we present an inference-based approach to estimating the atypicality of an individual's physiological data both at the level of measurement and physiological behavior. For this purpose, we use data from a cohort of subjects to infer, simultaneously, model representations for measurement disturbances and atypicality of physiological behavior. Using a case study on hematocrit (HCT), cardiac output (CO), and mean arterial pressure (MAP) measurements in response to hemorrhage and colloid infusions, we discuss the merits of the presented approach in deriving reliable subject atypicality and signal quality indicators for physiological data.
Recent studies suggest that atypical neural function, due to atypical neural structure, is associated with the behavioral symptoms of Autism Spectrum Disorder (ASD). Additionally, studies suggest that the atypical neural functions and structures associated with ASD change from early childhood to adulthood. This study is the first to develop a multiclass classification model to differentiate neural activity patterns of children and adults with and without ASD depicted by their EEG waveforms. In contrary to the conventional binary classification approaches used in state-of-the-art literature, the multi-class approaches learn the similarity, dissimilarity, common and differentiating patterns among all the categories present in the data. We collected 6 minutes of non-invasive resting-state EEG signals from 105 individuals that include ASD children and adults as well as typical children and adults. Since conventional supervised learning multi-class classifiers suffer from overfitting on limited clinical data, this study employed a few-shot learning mechanism, named prototypical network learning, that is adaptive to limited data and robust against data imbalance issues. Our developed model achieved 85% accuracy in multiclass classification. As the next step, we are developing an interpretable machine learning adaptation for prototypical learning to interpret the model inferences and highlight the brain wave patterns indicative of ASD in different stages of development.
Some medical implants act autonomously: they assess the current health status of a patient and administer treatment when appropriate. An improper treatment, however, can cause serious harm. Here, the decision logic leading to the treatment relies on data obtained from sensors --- an inherently imperfect medium. Coping with these inaccuracies requires the logic to be robust in the sense that slight perturbations in the measurements do not significantly alter the decision. Determining the extent to which an algorithm is robust automatically does not scale well for complex and opaque components. This is particularly problematic when machine learning is involved. Yet, the analysis is feasible for simpler safety-related components such as a runtime monitor, which observes the system and intervenes in a treatment when necessary. Its significantly lower complexity generally allows for providing static guarantees on the runtime behavior of the monitor. Complementing these guarantees with a robustness analysis constitutes a major step toward certifiable medical cyber-physical systems controlled by opaque, machine-learned components. Hence, this paper reports on ongoing research in the direction of a robustness analysis for the runtime monitoring framework RTLola.
The workshop is advised by the following steering committee members:
Julian M. Goldman, Massachusetts General Hospital/Harvard Medical School
Paul Jones, US Food and Drug Administration (FDA)
Insup Lee, University of Pennsylvania
Houssam Abbas, Oregon State University
Ezio Bartocci, TU Wien, Vienna University of Technology, Austria
Flavio H. Fenton, Georgia Institute of Technology, USA
Shan Lin, Stony Brook University, USA
Oleg Sokolsky, University of Pennsylvania, USA
Eugene Y. Vasserman, Kansas State University, USA
Yi Zhang, Massachusetts General Hospital, MDPnP Lab, USA